JP2003521775A - Method of efficiently performing scheduling process in electronic equipment - Google Patents

Abstract

(57) Summary In an apparatus and method for efficiently performing a scheduling process in an electronic device (112), an assignment manager (314) first evaluates a task scheduling request based on a request parameter. The scheduling request includes, for example, an execution interval (514) and a resource request (516). When the task scheduling request is granted, the assignment manager (314) registers the corresponding task (512) in the task table in which the priority is determined. The scheduling manager (316) refers to the task table to efficiently identify the next task (512) to be scheduled and executed in the electronic device (112).

Description

Detailed Description of the Invention

[0001]

TECHNICAL FIELD OF THE INVENTION

The present invention relates to a scheduling process, and more particularly, to an apparatus and method for efficiently performing a scheduling process in an electronic device.

[0002]

[Prior art]

Realizing a method for efficiently performing various processing tasks in electronic devices is an important issue for designers and manufacturers of modern electronic devices. For example,
The electronic device communicates with and shares data with other devices in the electronic network, which substantially improves the device capabilities and functionality within the individual electronic device. In some embodiments, the electronic network is implemented in a home environment, such as a personal computer, digital video disc (di).
Data and device resources are flexibly and effectively shared between various consumer devices such as digital video discs), digital set top boxes for digital broadcasting, high-performance television sets, and audio playback devices.

[0003]

[Problems to be Solved by the Invention]

Efficient management of task scheduling processing in a network of electronic devices is an important issue for designers of electronic devices. For example, the increasing demand for improved functionality and performance of equipment requires greater processing power and additional resources. The stringent requirements for processing or hardware raise economic costs such as increased manufacturing costs and reduced processing efficiency.

The size of the network is also one of the factors that affect the scheduling process of electronic devices. Communication in electronic networks becomes more complex as the number of individual devices or nodes increases. Here, a specific device in the electronic network is defined as a local device having a local software element, and another device in the electronic network is defined as a remote device having a remote software element. The local software module of the local device needs to transfer the data via the electronic network to the various remote software elements in the remote device. Here, by effectively managing a substantial number of electronic devices across a network, system users can be greatly benefited.

Moreover, while extending the capabilities of devices to perform various sophisticated processing tasks is beneficial to users, it also adds a burden to control and manage various devices in electronic networks. growing. For example, in the field of electronic networks with advanced capabilities to efficiently access data of digital television programs, process data of digital television programs, and display digital television programs, the amount of digital data to be processed and Due to the complexity, realization of efficient network communication technology is desired.

Due to the increasing demands on system processing resources and the substantial increase in the amount of data, realization of a new and efficient way of managing scheduling processing tasks is an important issue in the related electronic technology. . In view of the above-mentioned problems, it is an object of the present invention to provide a method for efficiently performing processing tasks in electronic devices for designers, manufacturers and users of modern electronic devices.

[0007]

[Means for Solving the Problems]

The present invention provides an apparatus and method for efficiently executing a scheduling process in an electronic device. In one embodiment, the instrument software first generates a scheduling request and supplies it to the assignment manager, which requests scheduling and execution of a particular task. This scheduling request preferably includes an execution interval T and a resource request corresponding to the requested task.

The execution interval T preferably includes information specifying a period in which task execution should be completed in the electronic device. The resource request includes, for example, information specifying how much of the total device resources are used to perform the corresponding task.

In response to the scheduling request, the assignment manager considers the available device resources and determines whether or not the scheduling of the requested task can be permitted. Furthermore, the allocation manager evaluates the request parameters and ensures that the duration of the execution interval T fulfills a predetermined execution condition. In one embodiment, this execution condition requires that the execution interval of each task be a power of 2 times the reference basic cycle, for example.

If sufficient resources are available and the execution interval T satisfies the execution condition, the allocation manager registers the requested task in a task table with priorities. In one implementation, the assignment manager ranks the tasks in the task table such that the task execution priority level is inversely proportional to the execution interval of each task.

The scheduling manager refers to the task table to specify the next task to be scheduled and executed in the electronic device. The scheduling manager then schedules and executes the next basic cycle by identifying the tasks that have not exhausted their allocated resources and have the highest priority (the one with the shortest execution interval). Select the task to be done.

When the task to be scheduled and executed next is specified, the scheduling manager refers to the “ready for execution” table to determine whether the specified next task is ready for execution. To do. If the next task is ready to be executed, the scheduling manager schedules the task in the electronic device and starts executing the task. In one implementation, the scheduling manager consults a "resource consumption" table that is continuously updated and indicates the amount of resources used to perform the current task.

This allows the scheduling manager to compare the used resources with the allocated resources and terminate the current task if the resources allocated to the current task have reached the limit. , Which allows other tasks to be scheduled and executed. As described above, according to the present invention, it is possible to effectively use the allocation manager, the task table, and the scheduling manager to efficiently schedule a sequence of tasks in an electronic device.

[0014]

DETAILED DESCRIPTION OF THE INVENTION

The present invention relates to improvements in electronic equipment. The following description discloses the present invention in such details that those skilled in the art can make and use the present invention based on the method of patent application and its requirements. Those skilled in the art can easily devise various modifications of the following preferred embodiments, and the principles described herein can be applied to other embodiments. That is, the present invention is not limited to the embodiments described below, but is construed to include the widest range corresponding to the principles and features described below.

The present invention provides an apparatus and method for efficiently executing a scheduling process in an electronic device, and an allocation manager that initially evaluates a task scheduling request based on predetermined request parameters. Request parameters include, for example, resource requirements and execution intervals. When the task scheduling request is granted, the assignment manager adds the corresponding task to the task table with priority.
The scheduling manager refers to the task table to efficiently identify the next task for scheduling and execution on the electronic device.

FIG. 1 is a block diagram showing the configuration of a network 110 of electronic equipment to which the present invention is applied. In this specific example, the network 110 is not particularly limited to such a configuration, but the device 112 (device A112 (a), device B11).
2 (b), root device 114, device C112 (c), device D112 (d), device E112 (e)). In a modification, the network 110 of electronic devices
May include various other devices or components in addition to or instead of these devices shown in FIG. In addition, in a modification, the network 110 may be connected and configured by another appropriate and appropriate method.

In the specific example shown in FIG. 1, the devices 112 in the network 110 include, but are not limited to, personal computers, printers,
It may be any kind of electronic device such as a digital video disc device, a television set, an audio system, a video tape recorder, a set top box for digital broadcasting. In the specific example shown in FIG. 1, the devices 112 communicate with each other using the network bus 132. The network bus 132 has a path 132 (a), a path 132 (b), a path 132 (c), a path 132 (d), and a path 132 (e). For example, the device B 112 (b) is connected to the device A 112 (a) via the path 132 (a) and is also connected to the root device 114 via the path 132 (b). Similarly, the root device 114 uses the path 13
2 (c) to the device C112 (c) and the path 132 (
device D112 (d) through device d112). Further, the device D112 (d
) Is connected to computer 116 via path 132 (e). Figure 1
In the specific example shown in FIG. 3, the network bus 132 is preferably based on the P1394 standard (1995 edition) for high performance serial bus in IEEE, which standard is incorporated herein by reference. To do. It should be noted that in variations, the network 110 may communicate and function using various other network interconnection schemes, and such forms are also within the scope of the invention.

In the specific example shown in FIG. 1, any device 112 in the network 110 can communicate with other devices 112. For example, the device E112 (e) is the device B.
When communicating with 112 (b), the device E112 (e) transmits the transfer data to the device D112 (d) via the path 132 (e), and the device D112 (d) takes the path 132 (d). The transfer data is transmitted to the root device 114 via. In response to this, the root device 114 transmits the transfer data to the device B 112 (b) via the path 132 (b). In the specific example shown in FIG. 1, the root device 114 supplies a master cycle start signal for synchronizing the isochronous process to the device 112 in the network 110. In other network implementations, any other network device 112 may be designed to act as a root device or cycle master.

FIG. 2 is a block diagram showing a specific example of the configuration of the device 112 in the network 110 according to the present invention. The device 112 includes, but is not limited to, a processor 212, an input / output (I / O) interface 214, a memory 216, a common device bus 226, and a bus interface 220. Processor 2
12, I / O interface 214, memory 216 and bus interface 22
0 are connected to each other via the common device bus 226.

In the embodiment shown in FIG. 2, processor 212 may be implemented with any suitable multipurpose microprocessor device. Memory 216 includes, but is not limited to, read-only memory,
It may be implemented by one or more suitable storage devices, including random access memory and various types of non-volatile memory such as floppy disk drives or hard disk drives. The I / O interface 214 controls an interface for communication with various compatible sources and / or partner devices.

In the present invention, the bus interface 220 controls the interface between the device 112 and the network 110. In the specific example shown in FIG. 2, the bus interface 220 communicates with another device 112 on the network 110 via the network bus 132. Further, the bus interface 220 is the common device bus 2
26, the processor 212, the I / O interface 214, and the memory 21.
6. Communicate with 6.

In the embodiment shown in FIG. 2, the instrument 112 is capable of performing various tasks including isochronous data and isochronous processing. The isochronous data usually includes information having a time constraint, and therefore the isochronous data needs to be transferred and processed at an appropriate timing. For example, video data that is displayed immediately needs to be delivered to an appropriate device at an appropriate timing so that jitter or interruption of the corresponding image being displayed does not occur. For this reason,
Equipment 112 preferably performs isochronous processing and other types of processing in temporal segments called "cycles."

Scheduling isochronous processing usually requires a finite period called “overhead”. The shorter the cycle time period, the shorter the time for performing the actual isochronous transfer. Therefore, the shorter the cycle time period, the more important the overhead becomes. In the example shown in FIG. 2, the cycle frequency is about 8 kHz and the cycle time period is about 125 μs.

FIG. 3 is a diagram showing a specific example of the configuration of the memory 216 shown in FIG. 2 according to the present invention. In the specific example shown in FIG. 3, memory 216 includes, but is not limited to, device software 312 and an allocation manager.
314, a scheduling manager 316, and a task table 318. In variants, the memory 216 may additionally or alternatively have elements different from those shown in FIG.

In the embodiment shown in FIG. 3, the instrument software 312 has software instructions that are executed by the processor 212 to implement various functions and operations in the instrument 112. The properties and functions of the device software 312 change depending on factors such as the type and usage of the host device 112.

In the embodiment shown in FIG. 3, the allocation manager 314 analyzes various scheduling request parameters to determine whether a particular task or process is instantiated on behalf of an entity such as the appliance software 312. . Figure 3
In the illustrated example, the scheduling manager 316 controls the scheduling and execution of certain tasks authorized by the allocation manager 314. In one embodiment of the invention, allocation manager 314 uses task table 31
8 manages and updates 8 and the scheduling manager 316 references the task table 318 in various task scheduling and task execution processes.
Allocation manager 314, scheduling manager 316, task table 3
Item 18 will be described later with reference to FIGS.

FIG. 4 is a diagram showing a concrete example of the task table 318 according to the present invention shown in FIG. In the specific example shown in FIG. 4, the task table 318 has task # 1 (5
12 (a)) to task #N (512 (d)). Each of task # 1 (512 (a)) to task #N (512 (d)) illustrated in FIG. 4 corresponds to a specific task, process, or function executed by the device 112. For example, these tasks may include desired processing or functions such as processor processing, memory access, data transfer, signal processing, and the like.

In the specific example shown in FIG. 4, each of task # 1 (512 (a)) to task #N (5
12 (d)) is an execution interval, "done" bit
And the corresponding resource requirements. That is, each task # 1 (512 (a
)) To task #N (512 (d)), for example, the execution interval #
1 (514 (a)) to #N (514 (d)), Danbit # 1 (518 (a)) to #N (518 (d)) associated with each, and Resource Request # associated with each. 1 (516 (a)) to #N (516 (d)). In a modification, the task table 318 may include various other elements in addition to or instead of the elements shown in FIG.

In the specific example shown in FIG. 4, the execution intervals # 1 (514 (a)) to #N (51).
4 (d)) is task # 1 (512 (a)) to task #N (512 (d)).
)) Contains the value “T” that specifies the period during which execution should be completed. Resource request #
1 (516 (a)) to #N (516 (d)) correspond to the corresponding task # 1 (512).
(A))-Information about the amount of resources required to execute task #N (512 (d)) is stored. Resource requests may be, but are not limited to, bus bandwidth requests, processing power requests, memory requests, and the like.

In the specific example shown in FIG. 4, resource requests # 1 (516 (a)) to #N (51
6 (d)) may be expressed as a percentage of the total amount of resources available on the device 112. In the modification, resource request # 1 (5
16 (a)) to #N (516 (d)) may be expressed in any suitable format required.

In the embodiment shown in FIG. 4, the instrument 112 sets the appropriate dambit 518 so that the corresponding task 512 in the current isochronous cycle.
Is executed. The resource request 516, the dambit 518, and the execution interval 514 will be described in detail later with reference to FIGS.

FIG. 5 shows a block diagram of an apparatus for performing a scheduling process according to the present invention. In variations, the scheduling process according to the present invention may be implemented using various other techniques and configurations.

In the specific example shown in FIG. 5, the device software 312 first sets the path 412.
To the allocation manager 314, which causes the device 112 to schedule and perform a particular task. The scheduling request preferably includes one or more request parameters. In the specific example shown in FIG. 5, this request parameter includes, for example, the execution interval T corresponding to the request task and the resource request.

As described with reference to FIG. 4, the execution interval T includes information that specifies the period in which the corresponding requested task should be executed in the device 112. The resource request also preferably includes information that represents how much of the total resources in device 112 are used to perform the corresponding task. In the specific example shown in FIG. 5, the request parameter of the resource request is
For example, the long-term average value of the resources required for the corresponding task (long-term averaging
age).

In response, the allocation manager 314 determines whether the scheduling of the requested task can be allowed in terms of the resources available on the device 112. In the specific example shown in FIG. 5, the allocation manager 314 adds new resource request parameters to the current resource allocation value of the device 112 so that the current scheduling request is 100% or more of the total amount of resources available at the device 112. Limit the allocated resources to within 100 percent by determining whether to request and deciding whether to grant the current scheduling request.

In addition, the allocation manager 314 evaluates the request parameters, thereby ensuring that the execution interval T meets predetermined execution specifications. The restrictions imposed on the execution intervals according to the present invention will be described later with reference to FIGS. 6 to 9.

If sufficient resources are not available, or if the execution interval T does not meet the execution conditions, the allocation manager 314 rejects the scheduling request and, via path 412, to the device software, a device application 312. Returns an error message. On the other hand, when sufficient resources are available and the execution interval T satisfies the execution condition, the allocation manager 314 adds the requested task to the task table 318 via the path 414. In the specific example shown in FIG.
The allocation manager 314 supplies the task table 318 with the execution interval 514 and the resource request 516 as request parameters (FIG. 4).

In the specific example shown in FIG. 5, the assignment manager 314 preferably uses task # 1 (512 (a)) to task #N (512 (d) in the task table 318.
)) Is performed to specify the priority of execution. In the specific example shown in FIG. 5, the allocation manager 314 uses the task # 1 (512 (a)) to the task #N (51).
2 (d)) based on the execution intervals # 1 (514 (a)) to #N (514 (d)), the task 512 having the shortest execution interval 514 is given the highest priority and the execution interval 5
14 gives the shortest task 512 the lowest priority, so that task # 1
(512 (a)) to task #N (512 (d)) are ranked. The allocation manager 314 grants the scheduling request from the device application 312 and returns a request grant message to the device application 312 via path 412.

In the embodiment shown in FIG. 5, the instrument 112 performs only a single task at any given time, which task is preferably a series of consecutive, each having exactly the same duration. It is executed in the context of the basic cycle. As described with reference to FIG. 2, in the specific example shown in FIG. 5, the basic cycle period consists of an isochronous cycle of 125 μs.

In the example shown in FIG. 5, during task execution, the scheduling manager 316 references task table 318 via path 415 to identify the next task to schedule and execute in device 112. As described above, the scheduling manager 316 next schedules and executes by identifying the task 512 with the highest priority (shortest execution interval) that does not consume the allocated resources in the current base cycle. Select a task.

When the next task for scheduling and execution is identified, the scheduling manager 316 looks up the “ready-to-run” table to put the identified next task in a ready state. Determine if there is. If the task is not registered in the "ready to run" table, the scheduling manager 316
Determines that the tasks listed in task table 318 are not ready for immediate execution.

If the next task identified is ready, the scheduling manager 316 schedules the task at the device 112 and begins execution. In the specific example shown in FIG. 5, the scheduling manager 316 is
Preferably, it monitors a "resources-consumed" table that shows the amount of resources that are continuously updated and used to perform the current task. The scheduling manager 316 compares the resource amount currently used with the resource amount allocated to the resource request 516, and if the resource allocation amount reaches the limit, terminates the current task.

In the embodiment shown in FIG. 5, the scheduling manager 316 preferably resets previous processing at the beginning of each basic cycle. In other words, the resources indicated by resource request 516 are preferably provided on a cycle-by-cycle basis. Therefore, at the beginning of each basic cycle, the scheduling manager 316 preferably references the task table 318 via path 415 and resumes task scheduling and execution based on task priority or execution interval. Thus, in the embodiment of the present invention, the allocation manager 3
14, the task table 318 and the scheduling manager 316 can be used to efficiently schedule a sequence of tasks on the device 112.

FIG. 6 is a timing chart of the execution intervals of the three tasks in the specific example of the present invention. The timing charts shown in FIG. 6 are shown in FIGS.
) 614 and FIG. 6 (C) 616. The timing chart shown in FIG. 6 is exemplary, and the invention may be implemented in the context of various other waveforms, execution intervals, tasks and timing relationships.

The timing chart shown in FIG. 6 represents a series of uninterrupted continuous basic cycles that occur regularly in device 112 as a timing reference for performing various tasks. 6 (A), 6 (B), and 6 (C) respectively represent different types of tasks scheduled and executed in the device 112. As described above, in this specific example, the device 112 executes only one of the tasks shown in FIG. 6 at any arbitrary time.

The waveform in FIG. 6A 612 illustrates a series of tasks a1-a4 that it is desirable to reliably execute at the beginning of each basic cycle. In the specific example shown in FIG.
The waveform of FIG. 6A 612 completes within the execution interval T1 (630) equal to the basic cycle. In this specific example, tasks a1 to a4 have the shortest execution interval T1.
Since it has (630), the tasks a1 to a4 have the highest priority with respect to scheduling, as described above.

On the other hand, the waveform in FIG. 6B 614 indicates tasks b1 and b2. In the example shown in FIG. 6, the waveform shown in FIG. 6B 614 is completed within the execution interval T2 (632) equal to 2 to the power of 1 of the basic cycle. In this specific example, tasks b1 and b2 have the second shortest execution interval T2 (632), so task b
1, b2 has the second highest priority for scheduling.

The waveform in FIG. 6C 616 indicates the task c1. In the example shown in FIG. 6, the waveform of FIG. 6 (C) 616 completes within an execution interval T3 (634) equal to 2 squared of the basic cycle. In this specific example, task c1 is
Having the longest execution interval T3 (634), task c1 has the lowest priority with respect to scheduling.

As described using FIG. 5 and this timing chart, the allocation manager 3
14 evaluates the scheduling request parameters received from the device software 312 and ensures that the execution period T fulfills strict execution conditions. In the specific example shown in FIG. 6, the above execution condition requires that the execution interval of each task be, for example, a power of 2 times the basic cycle.

That is, in the specific example shown in FIG. 6, each execution period T can be expressed by the following equation. T = (t _base ) 2 ⁿ Here, t _base represents the period of the basic cycle, and T represents the execution interval required for scheduling and executing the task in the device 112.

In variants, the execution intervals of the various tasks may be associated with the basic cycle in any suitable way that maintains a symmetric relationship between the various execution intervals.
For example, the execution condition of the device 112 may require that the execution period of each task corresponds to an integral multiple (eg, 3 or 4) of the basic cycle period.

As described above, the present invention enhances the efficiency of scheduling by imposing a constraint on the execution period of a task scheduled to be executed in the device 112. That is, according to the present invention, by limiting the execution interval,
It eliminates the skew between the start times of various tasks, which allows the scheduling process to work in a more predictable manner in a symmetric scheduling format.

FIG. 7 is a timing chart showing a scheduling sequence of the three tasks shown in FIG. 6 as a specific example of the present invention. In the modification, the present invention can generate various scheduling sequences different from the scheduling sequence shown in FIG. 7.

FIG. 7, like FIG. 6 described above, illustrates a series of consecutive basic cycles that occur at the instrument 112 as a timing reference for the scheduling and execution of various tasks. In the specific example shown in FIG. 7, each basic cycle described above is
Start at times 618, 620, 622, 624, 626.

In the specific example shown in FIG. 7, at time 618, the execution of task a1 (having the highest priority and the shortest execution interval) is scheduled. Task a1
Using the resources allocated to it, the first part of task b1 (having the second priority) is started following task a1. At time 620, when the next basic cycle begins, a cycle reset occurs and task a2 (with highest priority and shortest execution interval) is scheduled for execution.

When the resource allocated by task a2 is used, the last part of task b1 (having the second priority) is executed following task a2. Task b1
Using the allocated resources, the first part of task c1 (having the lowest priority) is started following task b1.

At time 622, when the next basic cycle begins, a cycle reset occurs and task a3 (with highest priority and shortest execution interval) is scheduled for execution. When task a3 uses the allocated resources, task a3 is followed by the second part of task c1 (which has the lowest priority).

When the next basic cycle is started in step 624, a cycle reset occurs and task a4 (with highest priority and shortest execution interval) is scheduled for execution. When task a4 uses the allocated resources, task a4 is followed by the last part of task c1 (which has the lowest priority). When the resource allocated to the task c1 is used, the device 112
Performs various system tasks until the next basic cycle begins at time 626.

FIG. 8 is a flowchart illustrating a process of handling a scheduling request according to the present invention. Alternatively, according to the present invention, the scheduling request may be processed by a different step and sequence from FIG.

In the example shown in FIG. 8, first, in step 812, the entity (eg, device application 312) sends a scheduling request and request parameters to the allocation manager 314 to request scheduling and execution of a particular task. . Subsequently, in step 814, the allocation manager 314
Whether or not to permit this scheduling request is determined based on various criteria including the criteria described with reference to FIG.

If the allocation manager 314 does not grant the scheduling request, then in step 816, the allocation manager 314 sends an error message to the entity that made the scheduling request and rejects the scheduling request. On the other hand, if the allocation manager 314 grants the scheduling request, step 81
8, the assignment manager 314 assigns the corresponding task to the task table 318.
(Fig. 4). Further, in step 820, the allocation manager 314
Sends a request grant message to the entity that made the scheduling request,
The process shown in FIG. 8 ends.

FIG. 9 is a flowchart showing the process of scheduling and executing a task according to the present invention. Alternatively, according to the present invention, tasks may be scheduled and executed according to steps and sequences different from those in FIG.

In the specific example shown in FIG. 9, first, in step 920, the scheduling manager 316 refers to the task table 318 and determines the priority assigning method such as the priority assigning method described with reference to FIG. Based on that, the next task to be scheduled is identified. When the next task is identified, the scheduling manager 316 determines whether the identified task is registered in the “ready for execution” table.

If this task is registered in the “ready for execution” table, step 92
At 4, the scheduling manager 316 schedules and executes the identified task. In step 928, the scheduling manager 316 compares the "resource consumption" table with the resources originally assigned to the task to determine whether the resource used has reached the resource limit for the particular task. To determine.

If the resource limit has been reached, in step 930 the scheduling manager 316 terminates the current task and the process shown in FIG.
Return to 20. On the other hand, if the allocated resources have not reached their limit,
In step 932, the scheduling manager 316 determines whether the start of a new basic cycle is scheduled. If the new basic cycle is not scheduled to start immediately, the process shown in FIG. 9 returns to step 928. On the other hand, if the new basic cycle is scheduled to be started immediately, the processing shown in FIG. 9 returns to step 920, and the task scheduling and execution processing described above is repeated.

The present invention has been described above based on the preferred embodiments of the present invention. From the above disclosure, those skilled in the art can easily devise other embodiments. For example, the present invention can be realized by using a configuration and a method different from the configurations and methods disclosed in the above-described preferred embodiments. Further, the present invention can be effectively applied to a system different from the system shown in the above-described preferred embodiment. Therefore, these and other variations on the preferred embodiments are within the scope of the invention, which is defined only by the appended claims.

[Brief description of drawings]

[Figure 1]   It is a block diagram which shows the structure of the electronic network to which this invention is applied.

[Fig. 2]   It is a block diagram which shows the structure of the apparatus based on this invention shown in FIG.

[Figure 3]   It is a figure which shows the structure of the memory based on this invention shown in FIG.

[Figure 4]   It is a figure which shows an example of the task table based on this invention shown in FIG.

[Figure 5]   It is a block diagram explaining the scheduling process based on this invention.

[Figure 6]   It is a timing chart which shows the execution interval of three tasks based on this invention.

FIG. 7 is a timing chart showing a scheduling sequence of the three tasks shown in FIG. 6 in a specific example of the present invention.

FIG. 8 is a flowchart showing a procedure for processing a scheduling request according to the present invention.

FIG. 9 is a flowchart showing a procedure of processing for scheduling and executing a task according to the present invention.

─────────────────────────────────────────────────── ─── Continued front page    (81) Designated countries EP (AT, BE, CH, CY, DE, DK, ES, FI, FR, GB, GR, IE, I T, LU, MC, NL, PT, SE, TR), OA (BF , BJ, CF, CG, CI, CM, GA, GN, GW, ML, MR, NE, SN, TD, TG), AP (GH, G M, KE, LS, MW, MZ, SD, SL, SZ, TZ , UG, ZW), EA (AM, AZ, BY, KG, KZ, MD, RU, TJ, TM), AE, AL, AM, AT, AU, AZ, BA, BB, BG, BR, BY, CA, C H, CN, CR, CU, CZ, DE, DK, DM, EE , ES, FI, GB, GD, GE, GH, GM, HR, HU, ID, IL, IN, IS, JP, KE, KG, K P, KR, KZ, LC, LK, LR, LS, LT, LU , LV, MA, MD, MG, MK, MN, MW, MX, NO, NZ, PL, PT, RO, RU, SD, SE, S G, SI, SK, SL, TJ, TM, TR, TT, TZ , UA, UG, UZ, VN, YU, ZA, ZW F-term (reference) 5B098 AA09 GA04 GA08

Claims (42)

[Claims] 1. A scheduling device for executing a scheduling process schedules an allocation manager (314) for processing a scheduling request by analyzing request parameters and a task (512) permitted by the allocation manager (314). A scheduling manager (316), the allocation manager (314) and the scheduling manager (316)
And a processor (212) for executing the scheduling process. 2. The scheduling device of claim 1, wherein the task (512) includes one or more isochronous operations requiring deterministic and guaranteed performance. 3. The scheduling device according to claim 1, wherein the scheduling process is executed in an electronic equipment network (110) conforming to the IEEE 1394 serial bus interconnection standard. 4. The task (512) is an appliance including any of consumer electronics, audio / visual equipment, set top boxes, and computing equipment (
The scheduling device according to claim 1, wherein the scheduling device is executed in 112). 5. The task (512) includes data transfer processing, processor processing,
The scheduling device according to claim 1, further comprising one of memory access processing and signal processing. 6. The scheduling device according to claim 1, wherein the request parameter includes at least one of a resource request (516) and an execution interval (514) for executing the task (512). 7. A scheduling device according to claim 6, comprising equipment software (312) for supplying a scheduling request for the task (512) to the allocation manager (314). 8. The allocation manager (314) is configured to request the resource (516).
) Is analyzed, and the total amount of allocated device resources is 1 of the available device resources.
7. The scheduling apparatus according to claim 6, wherein the scheduling is limited to within 100%. 9. The scheduling process is synchronized with a basic cycle that forms part of a continuous basic cycle sequence and serves as a timing reference for performing the task (512). 6. The scheduling device according to 6. 10. The allocation manager (314) is configured to perform the execution interval (514).
10. The scheduling apparatus according to claim 9, wherein the execution interval T is analyzed to ensure that the execution interval T satisfies the requirement of a symmetrical execution interval condition. 11. The request for the symmetrical execution interval condition is represented by the following formula, where t _base is a period of a basic cycle, and T is an execution interval required for scheduling and executing the task (512). 11. The method according to claim 10, wherein
A scheduling device as described. T = (t _base ) 2 ⁿ 12. The scheduling device according to claim 6, wherein the allocation manager (314) analyzes the scheduling request and returns either an error message or a request grant message. 13. The allocation manager (314) is configured to provide the resource request (51).
6) and / or the execution interval (514) together with the task (512).
7. The scheduling apparatus according to claim 6, wherein the task table is added to the task table. 14. The allocation manager (314) is configured to perform the execution interval (514).
14. The scheduling device according to claim 13, wherein a scheduling priority level inversely proportional to is assigned to the task (512). 15. The scheduling apparatus according to claim 14, wherein the scheduling manager (316) refers to the task table and identifies a task (512) to be scheduled based on the scheduling priority level. . 16. The scheduling apparatus according to claim 15, wherein the scheduling manager (316) refers to the execution preparation table to determine whether the task (512) can be immediately scheduled and executed. . 17. The scheduling device according to claim 15, wherein the scheduling manager (316) schedules the task (512) and starts execution of the task (512). 18. The scheduling manager (316) refers to a resource consumption table to determine whether the task (512) is using all the allocated resources, and the allocated resources are 18. The scheduling device according to claim 17, characterized in that the task (512) is terminated when the limit is reached. 19. The processor (212) resets the scheduling process when a new basic cycle is started.
A scheduling device as described. 20. The scheduling process includes a plurality of tasks (512) that are continuously scheduled and executed, and at any time, only one task of the plurality of tasks (512) is executed. The scheduling device according to claim 1, wherein: 21. A scheduling method for executing a scheduling process, comprising: processing a scheduling request by analyzing a request parameter by an allocation manager (314); and using the scheduling manager (316), the allocation manager (31).
4) Scheduling the task (512) permitted by the processor, and the processor (212) controlling the allocation manager (314) and the scheduling manager (316) to execute the scheduling process. Method. 22. The scheduling method of claim 21, wherein the task (512) comprises one or more isochronous operations requiring deterministic and guaranteed performance. 23. The scheduling method according to claim 21, wherein the scheduling process is executed in an electronic device network (110) conforming to the IEEE 1394 serial bus interconnection standard. 24. The task (512) is performed on a device (112) that includes any of consumer electronics, audio / visual devices, set top boxes, or computing devices. Scheduling method. 25. The task (512) includes any one of data transfer processing, processor processing, memory access processing, and signal processing.
The described scheduling method. 26. The scheduling method according to claim 21, wherein the request parameter includes at least one of a resource request (516) and an execution interval (514) for executing the task (512). 27. The task (512) is performed by the device software (312).
27. The scheduling method according to claim 26, comprising the step of providing a scheduling request for the allocation manager (314). 28. The allocation manager (314) comprises the resource request (51).
27. The scheduling method according to claim 26, wherein 6) is analyzed, and the total amount of assigned device resources is limited to within 100% of available device resources. 29. The scheduling process is part of a continuous basic cycle sequence and is synchronized with a basic cycle that serves as a timing reference for performing the task (512). 26. The scheduling method according to 26. 30. The allocation manager (314) is configured to perform the execution interval (514).
30. The scheduling method according to claim 29, wherein the execution interval T is analyzed to ensure that the execution interval T satisfies the requirement of a symmetrical execution interval condition. 31. The request for the symmetrical execution interval condition is represented by the following formula, where t _base is a period of a basic cycle, and T is an execution interval required for scheduling and executing the task (512). 31. The method according to claim 30,
The described scheduling method. T = (t _base ) 2 ⁿ 32. The scheduling method of claim 26, wherein the allocation manager (314) analyzes the scheduling request and returns either an error message or a request grant message. 33. The allocation manager (314) further comprises the resource request (51).
6) and / or the execution interval (514) together with the task (512).
27. The scheduling method according to claim 26, characterized in that is added to the task table. 34. The allocation manager (314) is configured to perform the execution interval (514).
The scheduling method according to claim 33, characterized in that a scheduling priority level inversely proportional to is assigned to the task (512). 35. The scheduling method according to claim 34, wherein the scheduling manager (316) refers to the task table and identifies a task (512) to be scheduled based on the scheduling priority level. . 36. The scheduling method according to claim 35, wherein the scheduling manager (316) refers to the execution preparation table to determine whether the task (512) can be immediately scheduled and executed. . 37. The scheduling method according to claim 35, wherein the scheduling manager (316) schedules the task (512) and starts execution of the task (512). 38. The scheduling manager (316) refers to a resource consumption table to determine whether the task (512) is using all the allocated resources, and the allocated resources are 38. The scheduling method according to claim 37, characterized in that the task (512) is terminated if a limit is reached. 39. The processor (212) resets the scheduling process when a new basic cycle is started.
The described scheduling method. 40. The scheduling process includes a plurality of tasks (512) that are sequentially scheduled and executed, and at any time, only one task of the plurality of tasks (512) is executed. 22. The scheduling method according to claim 21, wherein: 41. On a computer readable medium having program instructions for performing a scheduling process stored therein, the program instructions process a scheduling request by analyzing a request parameter by an allocation manager (314). Using the steps and the scheduling manager (316), the allocation manager (31
4) Scheduling the task (512) permitted by the processor, and causing the processor (212) to control the allocation manager (314) and the scheduling manager (316) to execute the scheduling process. A computer-readable medium characterized by the above. 42. In a scheduling device for executing a scheduling process, a scheduling request processing means for processing a scheduling request by analyzing request parameters, and a scheduling means for scheduling a task (512) permitted by the scheduling request processing means. And a control unit that controls the scheduling request processing unit and the scheduling unit to execute the scheduling process.